29 citations · 78 across the 18 of their papers we have counts for
Showing 2022Show all
2 papers · 1 filter
eess.SY2022
Learning-based Bounded Synthesis for Semi-MDPs with LTL Specifications
Ryohei Oura, Toshimitsu Ushio
This letter proposes a learning-based bounded synthesis for a semi-Markov decision process (SMDP) with a linear temporal logic (LTL) specification. In the product of the SMDP and t…
stat.ML2022★ 13 cited
Deep reinforcement learning under signal temporal logic constraints using Lagrangian relaxation
Junya Ikemoto, Toshimitsu Ushio
Deep reinforcement learning (DRL) has attracted much attention as an approach to solve optimal control problems without mathematical models of systems. On the other hand, in genera…